minoan-swarm

Warn

Audited by Snyk on Apr 23, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.90). The skill's templates and SKILL.md explicitly instruct teammates to perform web fetching and searching (e.g., "Prefer Firecrawl for web fetching" with example firecrawl scrape URL --only-main-content in SKILL.md and references/team-templates.md) and the discover_context.sh optionally queries GitHub via the gh CLI, meaning agents will ingest public web pages and issues (untrusted, user-generated content) as part of their workflow and could let page content materially influence agent decisions and tool use.

Issues (1)

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 23, 2026, 07:19 PM
Issues
1